Google AI (Gemini)

To enable Google AI models with Letta, set GEMINI_API_KEY in your environment variables.

You can use Letta with Google AI if you have a Google API account and API key. Once you have set your GEMINI_API_KEY in your environment variables, you can select what model and configure the context window size.

Enabling Google AI as a provider

To enable the Google AI provider, you must set the GEMINI_API_KEY environment variable. When this is set, Letta will use available LLM models running on Google AI.

Using the docker run server with Google AI

To enable Google Gemini models, simply set your GEMINI_API_KEY as an environment variable:

$# replace `~/.letta/.persist/pgdata` with wherever you want to store your agent data
>docker run \
>  -v ~/.letta/.persist/pgdata:/var/lib/postgresql/data \
>  -p 8283:8283 \
>  -e GEMINI_API_KEY="your_gemini_api_key" \
>  letta/letta:latest

Using letta run and letta server with Google AI

To chat with an agent, run:

$export GEMINI_API_KEY="..."
>letta run

This will prompt you to select a model:

$? Select LLM model: (Use arrow keys)
> » letta-free [type=openai] [ip=https://inference.memgpt.ai]
>   gemini-1.0-pro-latest [type=google_ai] [ip=https://generativelanguage.googleapis.com]
>   gemini-1.0-pro [type=google_ai] [ip=https://generativelanguage.googleapis.com]
>   gemini-pro [type=google_ai] [ip=https://generativelanguage.googleapis.com]
>   gemini-1.0-pro-001 [type=google_ai] [ip=https://generativelanguage.googleapis.com]
>   gemini-1.0-pro-vision-latest [type=google_ai] [ip=https://generativelanguage.googleapis.com]
>   gemini-pro-vision [type=google_ai] [ip=https://generativelanguage.googleapis.com]
>   gemini-1.5-pro-latest [type=google_ai] [ip=https://generativelanguage.googleapis.com]
>   gemini-1.5-pro-001 [type=google_ai] [ip=https://generativelanguage.googleapis.com]
>   gemini-1.5-pro-002 [type=google_ai] [ip=https://generativelanguage.googleapis.com]
>   gemini-1.5-pro [type=google_ai] [ip=https://generativelanguage.googleapis.com]
>   gemini-1.5-pro-exp-0801 [type=google_ai] [ip=https://generativelanguage.googleapis.com]
>   gemini-1.5-pro-exp-0827 [type=google_ai] [ip=https://generativelanguage.googleapis.com]

as we as an embedding model:

? Select embedding model: (Use arrow keys)
 » letta-free [type=hugging-face] [ip=https://embeddings.memgpt.ai]
   embedding-001 [type=google_ai] [ip=https://generativelanguage.googleapis.com]
   text-embedding-004 [type=google_ai] [ip=https://generativelanguage.googleapis.com]

To run the Letta server, run:

$export GEMINI_API_KEY="..."
>letta server

To select the model used by the server, use the dropdown in the ADE or specify a LLMConfig object in the Python SDK.

Built with